Kidney transplant prevalence and costs have been increasing steadily in the past few decades and this trend is anticipated to continue for years to come. Patient outcomes are heavily influenced by the amount of time they are waiting for a transplant and by the quality of care they are receiving up to the transplant. This paper intends to increase positive patient outcomes and decrease costs by identifying potential kidney transplant patients earlier than traditional methods. I use medical claims data to determine common risk factors of all patients who have received a kidney transplant. For the control group I include all patients who have not received a kidney transplant. I used a binary logistic regression utilizing common risk factors determined by the claims data to determine what factors are significant and which ones have a larger impact on predicting kidney transplantation. This approach attempts to predict patient health outcomes using claims data instead of clinical data which is often used in other research methods.
The results of my analysis were that the risk factors found in clinical research of kidney transplantation were the same risk factors found using medical claims data. I determined diabetes, hypertension and end stage renal disease were strong indicators of potential kidney transplantation using claims data alone. My conclusion is that medical claims data can be used in place of clinical data when clinical data is not available or does not exist.
","abstract_html":"<p>Kidney transplant prevalence and costs have been increasing steadily in the past few decades and this trend is anticipated to continue for years to come. Patient outcomes are heavily influenced by the amount of time they are waiting for a transplant and by the quality of care they are receiving up to the transplant. This paper intends to increase positive patient outcomes and decrease costs by identifying potential kidney transplant patients earlier than traditional methods. I use medical claims data to determine common risk factors of all patients who have received a kidney transplant. For the control group I include all patients who have not received a kidney transplant. I used a binary logistic regression utilizing common risk factors determined by the claims data to determine what factors are significant and which ones have a larger impact on predicting kidney transplantation. This approach attempts to predict patient health outcomes using claims data instead of clinical data which is often used in other research methods. </p> <p>The results of my analysis were that the risk factors found in clinical research of kidney transplantation were the same risk factors found using medical claims data. I determined diabetes, hypertension and end stage renal disease were strong indicators of potential kidney transplantation using claims data alone. My conclusion is that medical claims data can be used in place of clinical data when clinical data is not available or does not exist.</p>","abstract_has_math":false,"creators":["Dischinger, Jeffrey"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Economics & Finance","degree_department":null,"school":null,"contributors":["Chih Ming Tan"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2014,"date_issued":"2014-01-01T08:00:00Z","date_published":"2014-01-01T08:00:00Z","updated_at":"2026-07-24T03:26:30Z","subjects":["Diabetes, Hypertension, Kidney, Renal, Transplant"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://commons.und.edu/theses/1526","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Chih Ming Tan"]},{"key":"dc:creator","label":"Author","values":["Dischinger, Jeffrey"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"thesis:degree_discipline","label":"Discipline","values":["Economics & Finance"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Diabetes, Hypertension, Kidney, Renal, Transplant"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://commons.und.edu/theses/1526"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Kidney transplant prevalence and costs have been increasing steadily in the past few decades and this trend is anticipated to continue for years to come. Patient outcomes are heavily influenced by the amount of time they are waiting for a transplant and by the quality of care they are receiving up to the transplant. This paper intends to increase positive patient outcomes and decrease costs by identifying potential kidney transplant patients earlier than traditional methods. I use medical claims data to determine common risk factors of all patients who have received a kidney transplant. For the control group I include all patients who have not received a kidney transplant. I used a binary logistic regression utilizing common risk factors determined by the claims data to determine what factors are significant and which ones have a larger impact on predicting kidney transplantation. This approach attempts to predict patient health outcomes using claims data instead of clinical data which is often used in other research methods.
The results of my analysis were that the risk factors found in clinical research of kidney transplantation were the same risk factors found using medical claims data. I determined diabetes, hypertension and end stage renal disease were strong indicators of potential kidney transplantation using claims data alone. My conclusion is that medical claims data can be used in place of clinical data when clinical data is not available or does not exist.
"]},{"key":"dc:title","label":"Title","values":["Predicting Kidney Transplantation Using Prior Disease Diagnosis From Medicare Claims Data"]}]}],"canonical_facts":{"dc:contributor":["Chih Ming Tan"],"dc:creator":["Dischinger, Jeffrey"],"dc:description.abstract":["Kidney transplant prevalence and costs have been increasing steadily in the past few decades and this trend is anticipated to continue for years to come. Patient outcomes are heavily influenced by the amount of time they are waiting for a transplant and by the quality of care they are receiving up to the transplant. This paper intends to increase positive patient outcomes and decrease costs by identifying potential kidney transplant patients earlier than traditional methods. I use medical claims data to determine common risk factors of all patients who have received a kidney transplant. For the control group I include all patients who have not received a kidney transplant. I used a binary logistic regression utilizing common risk factors determined by the claims data to determine what factors are significant and which ones have a larger impact on predicting kidney transplantation. This approach attempts to predict patient health outcomes using claims data instead of clinical data which is often used in other research methods.
The results of my analysis were that the risk factors found in clinical research of kidney transplantation were the same risk factors found using medical claims data. I determined diabetes, hypertension and end stage renal disease were strong indicators of potential kidney transplantation using claims data alone. My conclusion is that medical claims data can be used in place of clinical data when clinical data is not available or does not exist.
"],"dc:identifier":["https://commons.und.edu/theses/1526"],"dc:subject":["Diabetes, Hypertension, Kidney, Renal, Transplant"],"dc:title":["Predicting Kidney Transplantation Using Prior Disease Diagnosis From Medicare Claims Data"],"thesis:degree_discipline":["Economics & Finance"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-07-24T03:26:30Z"}